Vision - Based Human Tracking with Color Detection for Autonomous Mobile Robot
This paper proposes to build an autonomous human tracking mobile robot which can solve the occlusion problem
during tracking. The robot can make human tracking efficiently by analysing the information obtained from a camera which
is equipped on the top of the robot. The system performs human detection by using Histogram of Oriented Gradient (HOG)
and Support Vector Machine (SVM) algorithms and then uses HSV colour detection system for detecting stranger. The color
detection method for tracking humans in indoor environments providing the target color is distinctive from the environment.
Kalman filter can estimate the target human when the human is occluded with walls or something. The experimental results
are given to prove the effectiveness of the proposed method.
Keywords - color detection, HOG, HSV, Human tracking, Kalman filter, Occlusion problem, SVM